© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33508
    Prev
    Next
    INDEX
    Explanations

    stability of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ool
    -0.07
    åĺ¿åĺ¿
    -0.07
    anton
    -0.06
    æĭį
    -0.06
    avin
    -0.06
    oot
    -0.06
     Tenant
    -0.06
     Chamber
    -0.06
     confisc
    -0.06
    æĬł
    -0.06
    POSITIVE LOGITS
    ezi
    0.08
    Dragging
    0.08
    гам
    0.08
    ByVersion
    0.07
    yage
    0.07
    xBF
    0.07
    åľ¨ä»»ä½ķ
    0.07
     Pej
    0.07
    ï¾Ł
    0.07
    æĭĸ
    0.07
    Activations Density 0.154%

    No Known Activations